© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42793
    Prev
    Next
    INDEX
    Explanations

    variable names and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    屿
    -0.07
    èĮĥæĸĩç½ij
    -0.06
    å°Ķé¡¿
    -0.06
    ruc
    -0.06
    mern
    -0.06
    æł·
    -0.06
    çīĩçīĩ
    -0.06
     infin
    -0.06
    磯
    -0.06
     expressions
    -0.06
    POSITIVE LOGITS
    AttributeValue
    0.09
     Nors
    0.07
    æľīåģ¿
    0.07
    uga
    0.07
    å°ıæľ¨
    0.07
    èĩªæµģ
    0.07
    aud
    0.07
    å§Ķ
    0.07
    çĭ
    0.07
    eya
    0.07
    Activations Density 0.019%

    No Known Activations